作者身份表示学习能否捕捉文体特征？
Can Authorship Representation Learning Capture Stylistic Features?
AI总结：
针对作者身份表示是否主要编码写作风格的疑问，通过一系列针对性实验验证了该表示对写作风格敏感，为其应对数据偏移及风格迁移等下游应用提供支撑。
摘要：
在计算语言学中，自动将作者的写作风格与其文本内容相分离是一个长期存在且或许难以攻克的难题。与此同时，带有作者标签的大型文本语料库的出现，使得近期能够以纯数据驱动的方式学习作者身份表示，用于作者身份归属任务——该任务表面上更依赖于对写作风格的编码，而非对内容的编码。然而，在这一代替任务上取得的成功，并不能确保此类表示能够捕捉写作风格，因为作者身份也可能与其他潜在变量（如主题）相关。为了更好地理解这些表示所承载信息的本质，特别是验证“它们主要编码写作风格”这一假设，我们通过一系列针对性实验系统地探究了这些表示。实验结果表明，为作者身份预测这一代替任务学习到的表示确实对写作风格敏感。因此，作者身份表示有望对某些类型的数据偏移（如随时间推移的主题漂移）具有鲁棒性。此外，我们的发现可能为需要文体表示的下游应用（如风格迁移）开辟道路。
英文摘要：
Automatically disentangling an author's style from the content of their writing is a longstanding and possibly insurmountable problem in computational linguistics. At the same time, the availability of large text corpora furnished with author labels has recently enabled learning authorship representations in a purely data-driven manner for authorship attribution, a task that ostensibly depends to a greater extent on encoding writing style than encoding content. However, success on this surrogate task does not ensure that such representations capture writing style since authorship could also be correlated with other latent variables, such as topic. In an effort to better understand the nature of the information these representations convey, and specifically to validate the hypothesis that they chiefly encode writing style, we systematically probe these representations through a series of targeted experiments. The results of these experiments suggest that representations learned for the surrogate authorship prediction task are indeed sensitive to writing style. As a consequence, authorship representations may be expected to be robust to certain kinds of data shift, such as topic drift over time. Additionally, our findings may open the door to downstream applications that require stylistic representations, such as style transfer.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
